The Support Betting Vector Machine: A quantitative approach on beating the betting market.
Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesisAlternative title
The Support Betting Vector Machine : kvantitativ studie om möjlighet att slå spelmarknaden. (Swedish)
The Support Betting Vector Machine has explored the possibility to beat the betting market by generating a positive return on investment (ROI). 6460 games from Premier League (UK) were used to predict if games would result in over or under 2.5 goals. For classication, Support Vector Machine was used with appliance of a method to get class probabilities. The class probabilities were used together with the betting strategy Kelly Criterion to determine if the predictions were suitable to bet on, in regards to generating a long term positive ROI. However, it was showed that Kelly Criterion was not suitable, and a simpler betting system was used, were one constant used was placed. Logistic Regression showed the best result, with a ROI of 3.9 percent.
Place, publisher, year, edition, pages
Probability Theory and Statistics
IdentifiersURN: urn:nbn:se:umu:diva-122688OAI: oai:DiVA.org:umu-122688DiVA: diva2:940552